APPLICATION OF NEUTROSOPHIC SET TO MULTICRITERIA DECISION MAKING BY COPRAS by Ioan Degău

Professor Romualdas BAUSYS Dr.Sc. Vilnius Gediminas Technical University Vilnius, Lithuania E-mail: romualdas.bausys@vgtu.lt Professor Edmundas Kazimieras ZAVADSKAS Dr.Sc. Vilnius Gediminas Technical University Vilnius, Lithuania E-mail: edmundas.zavadskas@vgtu.lt Professor ArtĹŤras KAKLAUSKAS Dr.Sc. Vilnius Gediminas Technical University Vilnius, Lithuania E-mail: arturas.kaklauskas@vgtu.lt APPLICATION OF NEUTROSOPHIC SET TO MULTICRITERIA DECISION MAKING BY COPRAS Abstract. The paper presents multicriteria decision making method with single value neutrosophic sets (SVNS), namely COPRAS-SVNS. The complex proportional assessment method (COPRAS) has shown accurate results for the solution of various multicriteria decision making problems in the engineering field. In this paper, a new extension of the crisp COPRAS method has been proposed. This extension is developed in the context of single value neutrosophic sets. The information processing flow has been proposed for the solution of the multicriteria decision-making problems. The proposed approach consists of the following steps: neutrosophication, solution of MCDM by the operations of the neutrosophic sets, de-neutrosophication. For the execution of the de-neutrosophication step a new version of the score function is proposed. The solution of the practical example of the selection of location for a liquefied natural gas terminal has been provided to illustrate correctness and the effectiveness of the proposed technique. Key words: multi-criteria decision making(MCDM), complex proportional assessment (COPRAS) method, neutrosophic set, selection of location, liquefied natural gas terminal, Baltic sea. JEL Classification: C02, C44, C61, C63 1. Introduction During the last decade a lot of the research efforts have been made to incorporate the vagueness of the initial information for the solution of the complex nature practical problems by multi-criteria decision making (MCDM) methods. Although the different types of the fuzzy sets have been introduced and applied to

Romualdas Bausys, Edmundas Kazimieras Zavadskas, Artūras Kaklauskas ________________________________________________________________ the solution of the MCDM problems(Esbouei et al (2014), Ghadikolaei et al (2014), Kaya and Kahraman (2014), Yazdani-Chamzini (2014),Meng and Chen (2014),Yu (2013)), they cannot take into account all sorts of uncertainties that arise in the solution of the real engineering problems. A theory of the neutrosophic sets originally proposed by Smarandache (1999, 2014) allows to deal with “knowledge of neural thought” and this “neutral” component distinct this set from the other approaches that are to model uncertain phenomena of information (Mardani et al (2015)). In fact the neutrosophic sets are a generalization of the “fuzzy” and “intuitionistic fuzzy” sets. However, the existing methods governed by fuzzy sets and their particular types are not convenient to solve decision making problem with neutrosophic information. By the logic of the neutrosophic sets each aspect of the problem is represented by the degree of the truth (T), a degree of the indeterminacy (I) and a degree of the falsity (F). In contrast to intuitionistic fuzzy sets where the degree of the uncertainty depends on the degree of membership and the degree of non-membership, by neutrosophic logic the value of the indeterminacy degree is independent of truth and falsity degrees. Recently the researches proposed some applications of the neutrosophic sets for the solution multi-criteria decision making problems. Recently, Ye (2013) and Majundar and Samanta (2014) have been studied similarity and entropy aspects applying single-valued neutrosophic sets in multi-criteria decision making approaches. Zhang and Wu (2014) develop a novel method for the solution of the single-valued neutrosophic multi-criteria decision making problems under the assumption of the incomplete weight information. During the recent years a lot of the approaches are proposed to extend the crisp MCDM methods into fuzzy environment in order to deal with uncertain information (Balezentis et al (2014), Baležentis and Zeng (2013), Patrascu (2013),Hajiaghaet al (2013), Zavadskas et al (2014), Zeng et al (2013)). The purpose of the present paper is to extend the crisp COPRAS method by application of the single valued neutrosophic set therefore proposing COPRASSVNS. The COPRAS method was developed by Zavadskas et al (1994). The structure of the paper is organized in the following way. Section 2 presents a description of the crisp COPRAS method. Section 3 brings the main concepts of a single valued neutrosophic set. Section 4 focuses on the description of the COPRAS-SVNS method and the application of the proposed method to the selection of a location for a liquefied natural gas terminal at east Baltic sea given Section 5. 2. The COPRAS method This multicriteria decision making technique was proposed by Zavadskas et al. (1994) can be generally expressed as follows. We consider decision-making

Application of Neutrosophic Set to Multicriteria Decision Making by COPRAS ________________________________________________________________ problem, which consists of m alternatives that must be assessed considering n criteria, and can be expressed as the value of the alternative by the criterion. The main idea of the COPRAS technique consists of the steps described below: Step1. Select the appropriate set of criteria that describes the chosen alternatives. Step2. Prepare decision-making matrix X:  x11 x X   21     xm1

x12 x22  xm 2

x1n   x1n       xmn  

Step 3. Determine the weights of the criteria

(1)

Step 4. Normalize decision-making matrix . The values of the normalized matrix are determined as xij 

xij

i 1 m

; i  1,2 ,...,m; j  1,2 ,...,n.

(2)

xij

Step 5. Compute weighted normalized decision-making matrix D, which components are calculated as dij  xij  w j ;i  1,2 ,...,m; j  1,2 ,...,n.

(3)

Step 6. Compute summation of the criterion values with respect to optimization direction for the each alternative P i 

 j 1

Lmax

d  ij ; Pi 

 j 1 dij ; Lmin

(4)

where d  ij values correspond to the criteria to be maximized and d ij values correspond to the criteria to be minimized. Step 7. Determine the minimal component of the Pi

Romualdas Bausys, Edmundas Kazimieras Zavadskas, Artūras Kaklauskas ________________________________________________________________ (5) P min  min Pi ; i  1,2 ,..., Lmin i

Step 8. Determine the score value of each alternative Qi :  P  min Qi  P i     Pi  

 j 1 P j  Lmin

 j 1

Lmin

P min P j

   

; j  1,..., Lmin

(6)

Step 9. Determine optimality criterion K for the alternatives: K  max Qi ; i  1,2 ,..., m.

(7)

Step 10. Determine the priority of the alternatives. The greater score value for the alternative corresponds to the higher priority (rank) of the alternative. 3. Neutrosophic sets We present a brief review of general concepts of neutrosophic set (Smarandache (1999)). Definition 1. Let X be space of the objects and x  X . A neutrosophic set A in X is defined by three functions: truth-membership function TA x  , an indeterminacy- membership function I A x  and falsity-membership function FA x  . These functions TA x  , I A x  and FA x  are defined on real standard or real

non-standard





I A x  : X  0  ,1 and

0 ,1 . That is T x : X  0 ,1  , F x  : X  0 ,1  . We have no any restriction on the

subsets

 









sum of TA x  , I A x  and FA x  , so 0   sup TA x   sup I A x   sup FA x   3 . 3.1. Single valued neutrosophic set

A single valued neutrosophic set (SVNS) has been defined as described in (Wang et al (2010)). Definition 2. Let X be a universal space of the objects and x  X . A ~ single valued neutrosophic set (SVNS) N  X can be expressed as



~ N  x ,TN~ x , I N~ x , FN~ x  : x  X



where TN~ x  : X  0 ,1 , I N~ x  : X  0 ,1 and FN~ x  : X  0 ,1

(8)

with 0  TN~ x   I N~ x   FN~ x   3 or all x  X . The values TN~ x  , I N~ x  and

Application of Neutrosophic Set to Multicriteria Decision Making by COPRAS ________________________________________________________________ FN~ x  correspond to truth-membership degree, the indeterminacy-membership ~ degree and the falsity-membership degree of x to N , respectively. For the case ~ when X consists of the single element, N is called a single valued neutrosophic number (Peng et al (2014)).For the sake of the simplicity, a single valued ~ neutrosophic number is expressed by N A  t A ,i A , f A  where t A ,i A , f A  0 ,1 and 0  t A  i A  f A  3 . ~ Definition 3. (Zhang and Wu (2014)) If N 1  t1 ,i1 , f1  and ~ N 2  t2 ,i2 , f 2  are two single valued neutrosophic numbers (SVNN), then the ~ ~ summation between N1 and N 2 can be expressed as follows ~ ~ N1  N2  t1  t2  t1t2 ,i1i2 , f1 f 2 

(9)

~ Definition 4. (Zhang and Wu (2014)) If N and 1  t1 ,i1 , f1  ~ N 2  t2 ,i2 , f 2  are two single valued neutrosophic numbers, then multiplication ~ ~ between N1 and N 2 can be expressed as follows

~ ~ N1  N2  t1t2 ,i1  i2  i1i2 , f1  f 2  f1 f 2 

(10)

~ Definition 5. (Zhang and Wu (2014)) If N 1  t1 ,i1 , f1  is a single valued neutrosophic number and    is an arbitrary positive real number then





~ N1  1  1  t1  ,i1 , f1 ,  0

(11)

Definition 6. (Majumdar and Samanta (2014)) If A   A1 , A2 ,..., An  and

(

)

B  B1 , B2 ,..., Bn  B = B1 ,B2 ,...,Bn are two single valued neutrosophic sets, then

separation measure between A and B applying the normalized Euclidian distance can be expressed as follows qn  A , B  

1 n t A xi   t B xi 2  i A xi   iB xi 2   f A xi   f B xi 2 3n i  1



i  1,2 ,...,n 

(12)

Romualdas Bausys, Edmundas Kazimieras Zavadskas, Artūras Kaklauskas ________________________________________________________________ ~ Definition 5. If N A  t A ,i A , f A  is a single valued neutrosophic number, a ~ ~ score function is mapped N A into the single crisp output S N A as follows

 

3  t A  2i A  f A ~ S NA  4

(13)

 

~ Where S N A  0 ,1 . This score function is the modification of the score function proposed by Sahin and Kucuk (2014) and allows us to have the results in the same interval as we deal with single valued neutrosophic numbers. ~ ~ Definition 6. Let N1 and N 2 be any two SVNNs. Therefore, ~ ~ ~ ~ ~ ~ If S N1  S N 2 then N1 is smaller than N 2 , N1  N 2 .

   

4. COPRAS with a single value neutrosophic set (COPRAS-SVNS) In this section, the extended COPRAS method is presented. The extension is performed by the application of the neutrosophic sets to model the information for the decision making problem. The general framework for the information processing of the proposed MCDM method can be illustrated as presented in Fig.1.

Neutrosophication

MCDM Engine

Crisp Input

De-Neutrosophication

Crisp Output Neutrosophic Rule Base

Figure 1. Information processing flow for MCDM with neutrosophic set

Application of Neutrosophic Set to Multicriteria Decision Making by COPRAS ________________________________________________________________ All information concerning the importance of the decision makers, individual expert evaluations regarding the ratings of alternatives via attributes and attribute weights usually are expressed in the crisp form. In the neutrosophication step we perform conversion of all crisp initial information into the single valued neutrosophic set. For this purpose weapply relationships between linguistic terms and single valued neutrosophic numbers. The set of linguistic terms used to rate the importance of the alternatives for the decision makers is presented in Table 1. Table 1. Linguistic terms to rate importance of the alternatives Linguistic terms SVNNs Extremely good (EG)/ 10 points (1.00, 0.00, 0.00) Very very good (VVG)/ 9 points (0.90, 0.10, 0.10) Very good (VG)/ 8 points (0.80, 0.15, 0.20) Good (G) / 7 points (0.70, 0.25, 0.30) Medium good (MG) / 6 points (0.60, 0.35, 0.40) Medium (M) / 5 points (0.50, 0.50, 0.50) Medium bad (MB) / 4 points (0.40, 0.65, 0.60) Bad (B) / 3 points (0.30, 0.75, 0.70) Very bad (VB) / 2 points (0.20, 0.85, 0.80) Very very bad (VVB) / 1 point (0.10, 0.90, 0.90) Extremely bad (EB) / 0 points (0.00, 1.00, 1.00) The performance of the group decision making applying COPRAS-SVNS approach can be described by the following steps. Step 1. Determine the importance of the experts. In the case when the decision is made by a group of the experts (decision makers), firstly the importance or share to the final decision of the each expert is determined. If a vector   1 ,2 ,...,k  is the vector describing the importance of the each expert, where

k  0 and

k 1 k  1 . K

Step 2. In the framework of this step, each decision maker performs his evaluations concerning the ratings of the alternatives with respect to the attributes and the attribute weights. If we denote by xijk ,i  1,2 ,..., m; j  1,2 ,..., n the k th expert’s evaluation of the i th alternative by the j th criterion. This evaluation is expressed in linguistic terms presented in the table 1. So the decision matrix for any particular expert can be constructed

Romualdas Bausys, Edmundas Kazimieras Zavadskas, Artūras Kaklauskas ________________________________________________________________  x k 11 x k 12  x k 1n   k  x 21 x k 22  x k 1n  (14) Xk          k  k k  x m1 x m 2  x mn  Step 3. Calculate the weights of the criteria. The aggregated weights of the criteria are determined by w j  1w(j1 )



 2 w(j 2 )  ... k w(j k ) 

K (w )  1   1 t k j  k 1



k

 

k

 K ( wk ) ,  i  k 1 j





( wk ) k

, f j k 1

(15)

Step 4.Construction of the aggregated weighted single valued decision matrix x11 ~ ~ x ~ X   21   ~  xm1

~ x12 ~ x

 ~ xm 2



~ x1n  ~  x1n       ~ xmn  

(16)



~ ~ xij  ~ tij , iij , f ij represents the rating of the alternative where any particular element ~

Ai with respect to j criterion and is determined as follows ~ xij  1 xij( 1 )



 2 xij( 2 )  ... k xij( k ) 

K (x )  1   1 t k ij  k 1



k

 

 K ( xk ) ,  i  k 1 ij

k

 

(17)

( x k ) k

, f ij k 1

Step 5. Determine the weighted decision matrix. Following Eq. (3), the weighted decision matrix can be expressed ~ as D  dij ,i  1,2 ,...,m; j  1,2,...,n, where dij  xij  w j . Applying Eq. (10), a single element of the weighted decision matrix can be calculated



dij  tijx t wj ,iijx  i wj  iijx i wj , fijx  f jw  fijx f jw



(18)

Application of Neutrosophic Set to Multicriteria Decision Making by COPRAS ________________________________________________________________ Step 6. Perform summation of the values for the benefit. Let

L  1,2 ,..., Lmax  be a set of the criteria to be maximized. Then the index of the benefit for each alternative can be determined

P i 

 j 1

Lmax

d  ij

(19)

where this summation of the single value neutrosophic numbers is performed applying Eq.(9). Step 7. Perform summation of the values for cost. Let L  1,2 ,..., Lmin  be a set of the criteria to be minimized. Then the index of the cost of each alternative can be determined

P i 

 j 1 d ij Lmin

(20)

Step 8. Determine the minimal value of the Pi . Step 9. Determine the score value of each alternative Qi . At the beginning the score values are calculated from the aggregated values for benefit and the cost S P i  and S Pi  applying Eq.(13). The score values of the alternatives van be expressed as

 S P   min Qi  S P i      S P min  

L i 1 S Pi  min

i  1

Lmin

S P min    S Pi  

(21)

Step 10. Determine optimality criterion K for the alternatives: K  max Qi ; i  1,2 ,..., m

(22)

Step 10. Determine the priority of the alternatives. The greater score value Qi for the alternative corresponds to the highest priority (rank) of the alternative.

Romualdas Bausys, Edmundas Kazimieras Zavadskas, Artūras Kaklauskas ________________________________________________________________ 5. Numerical examples As the numerical experiment, application example of the MCDM problem is solved in order to study the aspects of the implementation of the neutrosophic sets. A quite actually are location selection problems by the MCDM application: Dhenna and Mohanraj(2011) presented solution of the distribution center location problem; Elevli (2014) performed an evaluation of locations for the logistics center at Samsun (Turkey), Zavadskas et al (2015) solved a decision problem concerning the selection of the location for a liquefied natural gas terminal. We solved the same decision problem concerning the selection of the location site for liquefied natural gas terminal in order to study the performance of the proposed COPRAS-SVNS method. This problem consists of three alternatives and four groups of the criteria: social, environmental, economic and technical. All initial data transformed into neutrosophic sets. The provided decision matrix can be expressed as follows in Table 2. The weighted decision matrix is constructed applying Eq. (19) and is presented in Table 3. In the considered case S1-S3, A1-A5, E1-E2 andT1 are criteria for the benefit and E3-E4 andT2-T3are the cost criteria, the computed values P+i , P-i and Qi for each alternative are shown in Table 3. Therefore, the final ranking is A1  A3  A2 and this result completely coincides with the results obtained by crisp COPRAS approach (Zavadskas et al (2015)). These results are presented in Table 4. Analyzing the results presented in Table 4, it is not difficult to observe that Qi score values determined by COPRAS-SVNS approach are lower than the score values obtained by crisp COPRAS method. The proposed COPRAS-SVNS approach takes into account indeterminacy factor of the initial information and due this fact the score values are lower but this aspect do not change ranking results. On the basis of the results presented above, it is possible to conclude that COPRAS method provides robust and efficient framework for the solution of the MCDM problems applying the different set environments. 6. Conclusions There are a lot of the cases when solving multicriteria decision making problem it is necessary to deal with uncertain, imprecise and inconsistent information. Recently proposed neutrosophic sets enable us to model all types of the uncertainties in the most consistent way. In this paper, we have proposed the extended COPRAS method to deal with neutrosophic information. Neutrosophication step is performed applying a set of the linguistic terms that are used to express the rating of the alternatives in the neutrosophic environment. For the execution of the de-neutrosophication step a

Application of Neutrosophic Set to Multicriteria Decision Making by COPRAS ________________________________________________________________ Table 2. Initial decision matrix Alternatives Criteria Social S1 max S 2 max S 3 max Environmental A1 max

max A3 max A4 max A5 max Economic E1 max E2 max E3 min E4 min Technical T1 max T2 min T3 min Criteria A2

Social max S1 S 2 max S 3 max Environmental A1 max

(0.6, 0.35, 0.4) (0.7, 0.25, 0.3) (0.3, 0.75, 0.7)

(1.0, 0.0, 0.0) (0.9, 0.1, 0.1) (0.5, 0.5, 0.5)

(0.7, 0.25, 0.3) (1.0, 0.0, 0.0) (1.0, 0.0, 0.0) (0.9, 0.1, 0.1) (0.9, 0.1, 0.1)

(0.7, 0.25, 0.3) (0.7, 0.25, 0.3) (0.8, 0.15, 0.2) (1.0, 0.0, 0.0) (1.0, 0.0, 0.0)

(0.9, 0.1, 0.1) (1.0, 0.0, 0.0) (0.148, 0.874, 0.852) (0.27, 0.78, 0.73)

(0.7, 0.25, 0.3) (0.7, 0.25, 0.3) (0.426, 0.61, 0574) (0.351, 0.7, 0.649)

(1.0, 0.0, 0.0) (0.228, 0.822, 0.772) (0.217, 0.833, 0.783) Alternatives III

(0.6, 0.35, 0.4) (0.3798, 0.6702, 0.6202) (0.391, 0.659, 0.609) Weights

(0.3, 0.75, 0.7) (1.0, 0.0, 0.0) (1.0, 0.0, 0.0)

max

(1.0, 0.0, 0.0) (0.7, 0.25, 0.3)

A3 A4

max max

(0.9, 0.1, 0.1) (1.0, 0.0, 0.0)

(0.15, 0.875, 0.85) (0.4, 0.65, 0.4) (0.35, 0.7, 0.65) (0.25, 0.8, 0.75) (0.3, 0.75, 0.7) (0.35, 0.7, 0.65) (0.25, 0.8, 0.75) (0.25, 0.8, 0.75) (0.1, 0.9, 0.9)

Romualdas Bausys, Edmundas Kazimieras Zavadskas, Artūras Kaklauskas ________________________________________________________________ (1.0, 0.0, 0.0) (0.05, 0.95, 0.95) A5 max Economic (0.35, 0.7, 0.65) (1.0, 0.0, 0.0) (0.2, 0.85, 0.8) E1 max (1.0, 0.0, 0.0) (0.15, 0.875, 0.85) E2 max (0.426, 0.61, 0574) (0.4, 0.65, 0.6) E3 min (0.378, 0.672, 0.622) (0.25, 0.8, 0.75) E4 min Technical (0.2, 0.85, 0.8) (0.6, 0.35, 0.4) (0.35, 0.7, 0.65) T1 max (0.3925, 0.6575, 0.6075) (0.45, 0.575, 0.55) T2 min (0.391, 0.659, 0.609) (0.2, 0.85, 0.8) T3 min Table 3. Weighted decision matrix Criteria Alternatives I II III (0.036, 0.972, 0.964) (0.06, 0.956, 0.94) (0.018, 0.989, 0.982) S1 (0.037, 0.972, 0.963) (0.047, 0.966, 0.953) (0.053, 0.963, 0.948) S2 (0.011, 0.994, 0.989) (0.019, 0.988, 0.981) (0.037, 0.975, 0.963) S3 (0.074, 0.944, 0.926) (0.073, 0.944, 0.927) (0.105, 0.925, 0.895) A1 (0.075, 0.95, 0.925) (0.053, 0.963, 0.947) (0.053, 0.963, 0.947) A2 (0.075, 0.95, 0.925) (0.06, 0.9575, 0.94) (0. 068, 0.955, 0.932) A3 (0.027, 0.978, 0.973) (0.03, 0.975, 0.97) (0.03, 0.975, 0.97) A4 (0.014, 0.989, 0.987) (0.015, 0.988, 0.985) (0.015, 0.988, 0.985) A5 (0.063, 0.969, 0.937) (0.049, 0.974, 0.951) (0.07, 0.965, 0.93) E1 (0.053, 0.971, 0.947) (0.037, 0.9784, 0.963) (0.053, 0.97125, 0.947) E2 (0.021, 0.99, 0.979) (0.06, 0.967, 0.94) (0.06, 0.965, 0.94) E3 (0.024, 0.99, 0.976) (0.031, 0.986, 0.969) (0.033, 0.985, 0.967) E4 (0.07, 0.955, 0.93) (0.042, 0.971, 0.958) (0.042, 0.971, 0.958) T1 (0.021, 0.987, 0.979) (0.034, 0.979, 0.966) (0.035, 0.978, 0.965) T2 (0.009, 0.996, 0.991) (0.016, 0.992, 0.984) (0.016, 0.992, 0.984) T3 (0.423, 0.694, 0.688) (0.392, 0.707, 0.697) (0.429, 0.692, 0.68) P i (0.072, 0.965, 0.952) (0.133, 0.928, 0.912) (0.137, 0.926, 0.909) Pi 0.3366 0.3203 0.3413   S P i 0.0474 0.0914 0.094 S P i  0.4517 0.38 0.3993 Q

Application of Neutrosophic Set to Multicriteria Decision Making by COPRAS ________________________________________________________________

Table 4. Comparison of the ranking results by COPRAS and COPRASSVNS Location alternative Ai

COPRAS Rank

0.949

0.4517

0.587

0.38

0.593

0.3993

COPRAS-SVNS Rank

new version of the score function is proposed, which is defined in the interval [0, 1]. This interval is more consistent with general neutrosophic theory. The aspects of the application of the proposed COPRAS-SVNS method are studied considering the selection of the location site for liquefied natural gas terminal. The performed experiment shows numerical stability and consistency of the COPRAS method applying different set environments. This COPRAS-SVNS method enables us to deal with n-value neutrosophic logic. REFERENCES [1]

[2]

[3]

[4] [5]

Balezentis, T., Zeng, S., Balezentis, A. (2013), MULTIMOORA-IFN: A MCDM Method Based on Intuitionistic Fuzzy Number for Performance Management. Economic Computation & Economic Cybernetics Studies & Research, 48, 4, 85-102; Baležentis, T., Zeng, S. (2013), Group Multi-Criteria Decision Making Based upon Interval-Valued Fuzzy Numbers: An Extension of the MULTIMOORA Method. Expert Systems with Applications, 40, 2, 543–550; Dheena, P., Mohanraj, G. (2011), Multicriteria Decision-Making Combining Fuzzy Set Theory, Ideal and Anti-Ideal Points for Location Site Selection. Expert Systems with Applications, 38, 10, 13260-13265; Elevli, B. (2014), Logistics Freight Center Locations Decision by Using Fuzzy-PROMETHEE. Transport, 29, 4, 412-418; Esbouei, S. K., Ghadikolaei, A. S., Antuchevičienė, J. (2014), Using Fanp and Fuzzy Vikor for Ranking Manufacturing Companies Based on Their Financial Performance. Economic Computation and Economic Cybernetics Studies and Research, 48, 3, 141-162;

Romualdas Bausys, Edmundas Kazimieras Zavadskas, Artūras Kaklauskas ________________________________________________________________ [6] Ghadikolaei, A. S., Esbouei, S. K., Antuchevičienė, J. (2014), Applying Fuzzy MCDM for Financial Performance Evaluation of Iranian Companies. Technological and Economic Development of Economy, 20, 2, 274-291; [7] Hajiagha, S. H. R.; Hashemi, S. S.; Zavadskas, E. K. (2013), A Complex Proportional Assessment Method for Group Decision Making in an Interval-Valued Intuitionistic Fuzzy Environment. Technological and Economic Development of Economy, 19, 1, 22-37; [8] Kaya, I., Kahraman, C. (2014), A Comparison of Fuzzy Multicriteria Decision Making Methods for Intelligent Building Assessment. Journal of Civil Engineering and Management, 20, 1, 59-69; [9] Majumdar, P., Samanta, S.K. (2014), On Similarity and Entropy of Neutrosophic Sets. Journal of Intelligent and Fuzzy Systems, 26, 3, 1245-1252; [10] Mardani, A., Jusoh, A., Zavadskas, E.K. (2015), Fuzzy Multiple Criteria Decision-making Techniques and Applications – Two Decades from1994 to 2014. Experts Systems with Applications, 42, 4126-4148; [11] Meng, F., Chen, X. (2014), An Approach to Interval-Valued Hesitant Fuzzy Multi-Attribute Decision Making with Incomplete Weight Information Based on Hybrid Shapley Operators. Informatica, 25, 4, 617-642; [12] Patrascu, V. (2013), Neutrosophic Information in the Framework of Multivalued Representation. The 21-th Conf. Applied Industrial Mathematics, CAIM 2013, Bucharest, Romania; [13] Peng, J.J., Wang, J.Q., Zhang, H.Y., Chen, X.H. (2014), An Outranking Approach for Multi-Criteria Decision-Making Problems with Simplified Neutrosophic Sets; Applied Soft Computing, 25, 336346; [14] Sahin, R., Kucuk, A. (2014), Subsethood Measure for Single Valued Neutrosophic Sets. Journal of Intelligent and Fuzzy Systems, DOI: 10.3233/IFS-141304; [15] Smarandache, F. (1999), A Unifying Field in Logics. Neutrosophy: Neutrosophic Probability, Set and Logic. American Research Press, Rehoboth; [16] Smarandache, F. (2014), A Geometric Interpretation of the Neutrosophic Set, A Generalization of the Intuitionistic Fuzzy Set. Neutrosophic Theory and Its Applications, ed. Smarandache F., Europa Nova, Brussels, 2014, 27-35; [17] Wang, H., Smarandache, F., Zhang, Y. Q., Sunderraman, R. (2010), Single Valued Neutrosophic Sets. Multispace and Multistructure, 4, 410-413;

Application of Neutrosophic Set to Multicriteria Decision Making by COPRAS ________________________________________________________________ [18] Yazdani-Chamzini, A. (2014), An Integrated Fuzzy Multi Criteria Group Decision Making Model for Handling Equipment Selection. Journal of Civil Engineering and Management, 20, 5, 660-673; [19] Ye, J.(2013), Multicriteria Decision-making Method Using the Correlation Coefficient under Single-valued Neutrosophic Environment.International Journal of General Systems, 42, 4, 386– 394; [20] Yu, D. (2013), Intuitionistic Fuzzy Prioritized Operators and Their Application in Multi-Criteria Group Decision Making. Technological and Economic Development of Economy, 19, 1, 1-21; [21] Zavadskas, E.K., Kaklauskas, A., Sarka, V. (1994), The New Method of Multicriteria Complex Proportional Assessment of Projects. Technological and Economical Development of Economy, 1, 3, 131-139; [22] Zavadskas, E.K., Antuchevičienė, J., Hajiagha, S.H.R., Hashemi, S.S. (2014), Extension of Weighted Aggregated Sum Product Assessment with Interval-Valued Intuitionistic Fuzzy Numbers (WASPAS-IVIF).Applied Soft Computing 24, 1013-1021; [23] Zavadskas, E.K., Turskis, Z., Bagocius, V. (2015), Multi-Criteria Selection of a Deep-water Port in the Eastern Baltic Sea; Applied Soft Computing, 26, 180-192; [24] Zeng, S., Baležentis, T., Chen, J., Luo, J. (2013), A Projection Method for Multiple Attribute Group Decision Making with Intuitionistic Fuzzy Information. Informatica,24, 3, 485-503; [25] Zhang, Z., Wu, C. (2014), A Novel Method for Single-valued Neutrosophic Multi-Criteria Decision Making with Incomplete Weight Information. Neutrosophic Sets & Systems, 4, 35-49.